TW201807434A - Method and system for predicting the impact of forecasted weather, environmental and/or geologic conditions - Google Patents

Abstract

A system and method of predicting the impact of forecasted weather, environmental, and geologic events (that include one or more weather/environmental/geologic conditions) by determining a recurrence interval of each past condition in each location, determining the correlation between the past condition and the observable impact of the past event, calculating a predicted observable impact of each past event, calculating a predicted impact of each past event recurring by multiplying the predicted observable impact of the past event by the recurrence interval of the past condition, grouping the past events into a plurality of groups based on the predicted impact of the past condition recurring, determining a threshold for each group, receiving forecasted conditions, and determining the predicted impact of the forecasted conditions by comparing the forecasted conditions with the thresholds.

Description

Methods and systems for predicting the effects of weather, environmental and / or geological conditions

Forecasting the impact of future weather, environmental, and / or geological events is critical for companies and government organizations. However, the impact of these events does not depend solely on the magnitude of these events. For example, although a gale in Seattle, Washington, can cause significant damage and damage, winds of this magnitude are in Kansas with a history of strong winds (and infrastructure and population that can withstand and adapt to those conditions). The city of Wichita may not have such a big impact. Therefore, the prediction of the impact of a forecast event may vary based on the impact of similar events in that location and the return frequency of those events in that location. To date, the impact of future weather, environment, and geological events has been subjectively determined by people (eg, meteorologists, environmental scientists, geologists, etc.). However, these subjective judgments have several disadvantages. Except for the increase in the time it takes for a person (or a group of people) to make such subjective judgments, the subjective judgments are also inconsistent because the subjective judgment depends on the person (or people) who made the judgments. Skill level and disposal. Therefore, there is a need for a system that uses specific mathematical rules to predict the effects of weather, environmental, and geological events.

To overcome the shortcomings of the prior art, a system is provided that uses specific mathematical rules to predict the effects of weather, environmental, and / or geological events. Accordingly, a system and method are provided for predicting the effects of weather, environmental, and geological events (which include one or more weather / environment / geological conditions) by: determining one of each of the past conditions in each location Reproduce the time interval; determine the correlation between the past condition and the observable impact of the past event; calculate one of each past event to predict the observable impact; multiply the predicted observable impact of the past event by the past Calculate the predicted impact of each past event recurrence based on the recurring time interval of the condition; group the past events into a plurality of groups based on the predicted impact of the recurrence of the past condition; determine the threshold of each group Receive forecast conditions; and determine the predicted impact of the forecast conditions by comparing the forecast conditions with the threshold values.

Cross Reference to Related Applications This application claims priority to US Provisional Patent Application No. 62 / 343,547, filed on May 31, 2016, the entire contents of which are incorporated herein by reference. Reference is now made to the drawings that illustrate various views of an exemplary embodiment of the present invention. In the drawings and descriptions of the drawings herein, certain terms are used for convenience only and should not be considered as limiting the embodiments of the present invention. In addition, throughout the drawings and description below, the same numerals indicate the same elements. FIG. 1 is a block diagram of a risk index analysis system 100 according to an exemplary embodiment of the present invention. As shown in FIG. 1, the risk index analysis system 100 includes one or more databases 110, an analysis unit 180, and a graphical user interface 190. The one or more databases 110 include historical weather data 112, historical weather impact data 114, and forecast weather conditions 116. Although most embodiments are described below with reference to predicting the effects of forecasting weather conditions, in some embodiments, the hazard index analysis system 100 may be used to predict the effects of forecasting environmental conditions. Therefore, the one or more databases 110 may also include historical environmental data 122, historical environmental impact data 124, and predicted environmental conditions 126. In other embodiments, the hazard index analysis system 100 may be used to predict the effects of forecasting geological conditions. Therefore, the one or more databases 110 may also include historical geological data 132, historical geological impact data 134, and predicted geological conditions 136. The historical weather data 112 contains information indicating the location, time, and severity of past weather events. Past weather events may include, for example, hurricanes, tornadoes, thunderstorms, hail, floods, lightning, blasts, snow, floods, droughts, extreme temperatures, and the like. Each weather event includes one or more weather conditions (eg, snow, rain, ice, wind, heat, cold, etc.). The severity of each past weather event can be measured based on accumulated snowfall, accumulated rainfall, accumulated ice, wind speed, high temperature, and low temperature. Historical weather data 112 may be received from publicly available sources (eg, National Oceanic and Atmospheric Administration (NOAA) storm event database), private sources (eg, AccuWeather Corporation, AccuWeather Enterprise Solutions Corporation), and the like. Historical weather impact data 114 includes information indicating damage and disruption associated with past weather events. Damage and damage associated with past weather events can include direct damage to property and crops and indirect damage attributable to past weather events (e.g., power outages, lost sales, shipment delay information, reduced consumer spending, reduced Visits to retail and service locations, increased traffic speeds, etc.). Available from publicly available sources (e.g., NOAA Storm Event Database, which aggregates data from counties, states, federal emergency management officials, local law enforcement officials, skywarn observers, U.S. National Weather Service (NWS) damage investigations, clipping services, insurance, Information from the public, etc.), industry-specific commercial and non-commercial entities (eg, insurance claims information), third-party sources, etc. receive historical weather impact data 114. The historical weather impact data 114 may also include client-specific data (received from a client), and the danger index analysis system 100 uses the client-specific data to determine the client-specific impact of past weather events and predict the weather conditions 116 for the client Specific impact. Forecast weather conditions 116 include indications of forecast weather conditions (e.g., snow, rain, ice, wind, heat, cold, etc.) and events (e.g., hurricane, tornado, thunderstorm, hail, lightning, blast, snow, flood, drought, extreme, Temperature, etc.). Available from AccuWeather, AccuWeather Enterprise Solutions, the National Weather Service (NWS), the National Hurricane Center (NHC), other government agencies (such as the Environment Canada, the British Meteorological Agency, the Japan Meteorological Agency, etc.), private companies (such as Vaisalia National Lightning Detection Network, Weather Decision Technologies, Inc., and individuals (such as members of the Spotter Network) receive forecast weather conditions and events. Historical environmental data 122 contains instructions for past environmental events and environmental conditions (e.g., pollution, deforestation, population decline, climate change, meteorological conditions, uninhabitable, biodegradable pollution, non-biodegradable pollution, air pollution, noise pollution , Noise pollution, thermal pollution, water pollution, etc.). Historical environmental data 122 may be received from publicly available sources (eg, NOAA, US Geological Survey, etc.), private sources, and the like. Historical environmental impact data 124 contains information indicating damage and destruction associated with past environmental events. Damage and damage associated with past environmental events may include direct damage to property and crops and indirect damage attributable to past environmental events (e.g., power outages, sales losses, shipment delay information, reduced consumer spending, reduced Visits to retail and service locations, increased traffic speeds, etc.). The historical environmental impact data 124 may also include client-specific data (received from a client), and the danger index analysis system 100 uses the client-specific data to determine the client-specific impact of past environmental events and predict and forecast the environmental conditions 126 of the client Specific impact. Forecast environmental conditions 126 include instructions for forecasting environmental events and forecasting environmental conditions (e.g., pollution, deforestation, population decline, climate change, meteorological conditions, uninhabitable, biodegradable pollution, non-biodegradable pollution, air pollution, noise Pollution, noise pollution, thermal pollution, water pollution, etc.), the forecast location, forecast time and forecast severity. Predictive environmental conditions can be received from AccuWeather, AccuWeather Enterprise Solutions, the National Weather Service (NWS), the US Geological Survey, other government agencies, private companies, and more. Historical geological data 132 contains information indicating the location, time, and severity of past geological events and geological conditions (eg, erosion, glacial action, volcanic eruption or discharge, earthquake, tsunami, avalanche, landslide, earth flow, etc.). Historical geological data 132 may be received from publicly available sources (eg, NOAA, US Geological Survey, etc.), private sources, and the like. Historical geological impact data 134 contains information indicating damage and destruction associated with past geological events. Damage and damage associated with past geological events may include direct damage to property and crops and indirect damage attributable to past geological events (e.g., power outages, sales losses, shipment delay information, reduced consumer spending, reduced Visits to retail and service locations, increased traffic speeds, etc.). Historical geological impact data 134 may also include client-specific data (received from a client), and the danger index analysis system 100 uses client-specific data to determine client-specific effects of past geological events and predict and predict geological conditions of the client 136 Specific impact. The predicted geological conditions 136 include information indicating the predicted location, predicted time, and predicted severity of predicted geological events and predicted geological conditions (eg, erosion, glacial action, volcanic eruption or discharge, earthquake, tsunami, avalanche, landslide, earth flow, etc.). Forecast geological conditions can be received from AccuWeather, AccuWeather Enterprise Solutions, the National Weather Service (NWS), the US Geological Survey, other government agencies, private companies, and more. FIG. 2 is a diagram illustrating an overview of a structure 200 of a risk index analysis system 100 according to an exemplary embodiment of the present invention. As shown in FIG. 2, the architecture 200 may include one or more connected to a plurality of remote computer systems 240 (such as one or more personal systems 250 and one or more mobile computer systems 260) via one or more networks 230. Servers 210 and one or more storage devices 220. The one or more servers 210 may include an internal storage device 212 and a processor 214. The one or more servers 210 may be any suitable computing device including, for example, an application server and a web server hosting a website accessible by the remote computer system 240. The one or more storage devices 220 may include an external storage device and / or an internal storage device 212 of one or more servers 210. The one or more storage devices 220 may also include any non-transitory computer-readable storage medium, such as an external hard disk array or solid state memory. The network 230 may include any combination of the Internet, a cellular network, a wide area network (WAN), a local area network (LAN), and the like. Communication over the network 230 may be achieved through wired and / or wireless connections. A remote computer system 240 may be any suitable electronic device configured to send and / or receive data via the network 230. A remote computer system 240 may be, for example, a network-connected computing device, such as a personal computer, a notebook computer, a smart phone, a digital assistant (PDA), a tablet computer, a notebook computer, a portable Type weather detector, a global positioning satellite (GPS) receiver, a network-connected vehicle, a wearable device, etc. A personal computer system 250 may include an internal storage device 252, a processor 254, an output device 256, and an input device 258. The one or more mobile computer systems 260 may include an internal storage device 262, a processor 264, an output device 266, and an input device 268. An internal storage device 212, 252, and / or 262 may include one or more non-transitory computer-readable storage media (such as a hard disk or solid-state memory) for storing software instructions that are stored in a processor When executed at 214, 254, or 264, the relevant parts of the features described herein are implemented. A processor 214, 254, and / or 264 may include a central processing unit (CPU), a graphics processing unit (GPU), and the like. A processor 214, 254, and 264 may be implemented as a single semiconductor chip or more than one chip. An output device 256 and / or 266 may include a display, a speaker, an external port, and the like. A display may be any suitable device configured to output visible light, such as a liquid crystal display (LCD), a light emitting polymer display (LPD), a light emitting diode display (LED), an organic light emitting diode display ( OLED) and so on. The input devices 258 and / or 268 may include a keyboard, a mouse, a trackball, a static or video camera, a touch pad, and the like. A touch pad can be overlapped or integrated with a display to form a touch-sensitive display or touch screen. Referring again to FIG. 1, the one or more databases 110 may be any organized collection of information, stored on a single tangible device or multiple tangible devices, and may be stored on, for example, one or more storage devices 220 in. The analysis unit 180 may be implemented by software instructions stored on one or more of the internal storage devices 212, 252, and / or 262 and executed by one or more of the processors 214, 254, or 264. The graphical user interface 190 may be any interface that allows a user to input information for transmission to the risk index analysis system 100 and / or output information received from the risk index analysis system 100 to a user. The graphical user interface 190 may be implemented by software instructions stored on one or more of the internal storage devices 212, 252, and / or 262 and executed by one or more of the processors 214, 254, or 264. FIG. 3 is a flowchart of a process 300 for predicting the effects of weather conditions. The program 300 may be executed by, for example, the analysis unit 180. Observable effects of at least some of the past weather events are determined in step 302. As described above, historical weather impact data 114 includes information indicating damage and disruption associated with past weather events. In the simplest embodiment, the impact of a past weather event is the cost of physical damage (eg, measured in U.S. dollars) caused by such weather events (eg, as summarized by a NOAA storm event database). In other embodiments, the total observable impact of a past weather event is determined by adding the cost of physical damage caused by the weather event plus indirect damage associated with the weather event (e.g., power outage, sales Losses, lost productivity, reduced consumer spending, reduced visits to retail and service locations, increased traffic speeds, delays in shipments, etc.) (measured in U.S. dollars, man-hours, etc.) to determine One objective estimate of the total observable impact of the weather event. Finally, in other embodiments, the hazard index analysis system 100 can be used to predict one particular effect of a forecast weather event. In these embodiments, the impact of a weather event is the cost of that particular observable impact. The impact of individual weather events is by spatially combining the damage and destruction information contained in historical weather impact data 114 with the weather event information contained in historical weather data 112 (e.g., combining observable damage and destruction information by location and date And weather conditions information). 4 is an illustration of a weather event (in this example, an event that includes snow) in a location (in this example, Alamosa County, Colorado) having analysis performed in accordance with an exemplary embodiment of the present invention Sex form. As shown in Figure 4, some weather events include an objective estimate of the observable impact ("IMPACT") of the weather event. FIG. 5 is a weather event (in this example, an event that includes snow) in another location (in this example, Lichfield, Illinois) with analysis performed in accordance with an exemplary embodiment of the present invention An exemplary form. As shown in Figure 5, some weather events include an objective estimate of the observable impact ("IMPACT") of the weather event. As described in detail below, each row contains information about a weather event, where: Ÿ “METAR” is a location identified by a weather terminal aviation routine weather report (METAR) station; Ÿ NMETAR is the numerical name of a METAR station; Ÿ DATE is The date of the weather event; SNOWFALL is the total daily snowfall in inches; POPULATION is the estimated population in 2012; ELEVATION is the height (in meters) above sea level; IMPACT is from Historical weather event impact data 114 The total observable impact of the sum of reports near the METAR station; SNOW_EVENTS is the total number of days of snowfall in the data set; Ÿ MAGNITUDE is the weather when sorted according to the daily total snowfall ("SNOWFALL") Event ranking; Ÿ N is the number of years in the data set; Ÿ R is the number of years that a snowfall event has exceeded at least once calculated for the probability; Ÿ T is (N + 1) / MAGNITUDE, which is called "a recurrence interval Ÿ P is 1 / T, which has the probability of recurring one of the events at time interval T; Ÿ PE is 1- (P ** R), also known as "excess probability", which is described as the risk of failure ( For example, 10 years Snow has a 10% probability of occurrence in any given year, or PE = 0.10); W_IMPACT is IMPACT / POPULATION (weighted observable impact); P_IMPACT is as (for example) by the regression algorithm determined in step 310 The observable impact of the judgment is observed; Ÿ IMPACT_VALUE is T * P_IMPACT; Ÿ IMPACT_INDICATOR is the result of fitting the data distribution to a series of IF statements in 10 categories from 1 to 10, where 10 is the highest IMPACT_VALUE and 1 is the lowest IMPACT_VALUE. Referring again to FIG. 3, the observable effects of each of the past weather events are weighted by the population in step 304 to consider the fact that events in less populated areas will have a greater impact in more populated areas. As shown in the examples in Figures 4 and 5, the weighted observable effect W_IMPACT is IMPACT / POPULATION. Each weather event contains one or more related weather conditions. For example, a winter storm may include both snowfall (e.g., measured in inches) and low temperature (e.g., measured in degrees Fahrenheit). The historical weather data 112 contains information indicating these past weather conditions. For each of the past weather events, in step 306, the risk index analysis system 100 determines one or more relevant weather conditions (eg, snow, rain, ice, wind, temperature, etc.). In step 308, it is determined that the possibility that each of the past weather conditions will reoccur according to the magnitude is statistically referred to as a regression frequency. As shown in the examples in Figure 4 and Figure 5: Ÿ N is the number of years in the data set; Ÿ R is the probability calculation, the number of years that a snowfall event has exceeded at least once; Ÿ T is (N + 1) / MAGNITUDE, It is called "a recurrence time interval"; Ÿ P is 1 / T, which has the probability of recurring one of the events of time interval T; and Ÿ PE is 1- (P ** R), also known as "over "Probability", which is described as the risk of failure (for example, a 10-year snowfall has a 10% probability of occurrence in any given year, or PE = 0.10). In step 310, for each of the relevant weather conditions, a correlation is determined between the past weather conditions (and other explanatory variables) and the observable effects of the past weather conditions. For example, the hazard index analysis system 100 may use a regression algorithm that uses one of multiple regression factors (independent variables) for W_IMPACT (dependent variable), which follows the following equation ,among them system Predictors; and Regression coefficient. For example, one of the initial regression models for snowfall can determine To determine the additional predicted variables for snowfall ( Etc.), the residuals from the initial regression model can be plotted in ArcGIS, and using a cluster analysis, the locations can be grouped into different regional groups. A regression algorithm will then be performed on several groups, where each group has a predictive variable for each potential Unique coefficient . Additional predictive variables can be PE (exceeding variables), height, number of households, demographic information, seasonal measures, etc. Therefore, for each location of a past weather event, the hazard index analysis system 100 determines a formula for predicting the weather conditions (eg, snow, rain, ice, wind, temperature, etc.) and the observable effects of additional features of the location. Obviously, the coefficients are determined separately for each weather condition and location ( ) And additional predicted variables ( ). In step 312, for each location of a past weather event, the danger index analysis system 100 calculates the predicted observable impact of each of the past weather conditions. As shown in the examples in FIGS. 4 and 5, the predictable observable impact (P_IMPACT) is calculated based on the amount of SNOWFALL and other predicted variables using the formula determined by the regression algorithm in step 310. The hazard index analysis system 100 is used to predict the impact of future weather conditions, which varies based on both the observable impact stored in the historical weather impact data 114 and the frequency with which the location experiences these forecast weather conditions. In other words, a weather event that occurs less frequently in a particular location may have a greater impact on that location than those frequent occurrences of that same weather condition in that location. Therefore, in step 314, the predicted effect of past weather conditions recurrence is determined. As shown in the examples in Figures 4 and 5, the predicted impact (IMPACT_VALUE) of the recurrence of past weather events is the time interval (T) times the predicted observable impact (P_IMPACT). In step 316, for each place of a past weather event, the past weather events are sorted according to the predicted impact of the past weather event recurrence. As shown in the examples in Figs. 4 and 5, the past weather events are sorted according to the predicted impact (IMPACT_VALUE) of past weather event recurrences. In step 318, for each place of a past weather event, the past weather events are grouped based on the predicted impact (IMPACT_VALUE) of the past weather event recurrence. Sort past weather events into groups. For example, a Jenks optimization method can be used to assign each of the past weather events to several groups (eg, 10 groups) based on the predicted impact (IMPACT_VALUE) of the past weather event recurrence. Using the Jenkins optimization method (also known as natural segmentation classification method), each of the weather events is placed in one of these groups in order to minimize the average deviation of the average of each group and the group, while maximizing The deviation between the average of each group and other groups. In other words, the method seeks to reduce the number of variations within a group and maximize the number of variations between groups. As shown in the example in FIG. 4, five weather events with the highest IMPACT_VALUE are placed in the IMPACT_INDICATOR group 10, and weather events with the next highest IMPACT_VALUE are placed in the IMPACT_INDICATOR group 9 and so on. In step 320, for each location of a past weather event, a threshold value for each group is determined. In one embodiment, the threshold of each group may be the minimum amount of weather conditions in the group. Using the example in FIG. 4, the hazard index system 100 may determine that the threshold of the group 10 is a weather event equal to 7.0 inches of snowfall (ie, the minimum amount of snow in the group 10). In another embodiment, the threshold of each group may be the maximum amount of weather conditions in the next group. Using the example in FIG. 4, the threshold for group 10 will be 6.7 inches of snowfall (eg, the highest amount of snowfall in group 9). In this embodiment, the threshold of group 1 will be zero. In other embodiments, the threshold of each group may be between the minimum amount of weather conditions in the group and the maximum amount of weather conditions in the next group. Using the example in Figure 4, the threshold for Group 10 will be between 7.0 inches and 6.7 inches of snowfall. Steps 312 to 320 are performed for each weather condition in each location of a past weather event. Therefore, the hazard index analysis system 100 determines a number of thresholds (e.g., 10) for each of a plurality of weather conditions (e.g., snow, rain, ice, wind, heat, cold) in various locations of a past weather event. Threshold). In step 322, a threshold for the location of past weather events for additional geographic locations may be interpolated. As described above with reference to step 302, each past weather event and the impact of each past weather event may be spatially combined based on proximity to several discrete locations (e.g., locations of a METAR station). In order to determine the threshold of additional geographic locations, the hazard index analysis system 100 may use a kriging technique to interpolate the threshold to a smooth grating surface that contains the entirety of the hazard index analysis system 100 Thresholds for geographic locations in the coverage area (e.g., continental U.S.A. and the lower mainland provinces of Canada). The forecast weather conditions are received in step 324. Forecast weather conditions can be for any period of time, from an hour to a seasonal forecast or even a year forecast. Therefore, the hazard index analysis system 100 can be used to predict not only the impact of a specific weather event, but also the impact of all weather events that may affect various locations over a long period of time. The predicted effect of the forecast weather conditions is determined in step 326. Compare the predicted weather conditions in each location with the threshold of the location to determine the predicted impact of those weather conditions. Using the example shown in Figure 4, if a forecast includes a 10-inch snowfall in Alamosa County, Colorado, the impact of this weather condition is classified as a 10 because the forecast snowfall is greater than that of group 10. Limit. The predicted effects of forecasting weather conditions are output via GUI 190. The predicted effects of weather conditions can be output in a large number of formats, including organizational data, graphic images (GIS layer), etc. Depending on the particular use or application, other presentation formats may be utilized, such as audio and video displays. 6 to 7 illustrate the predicted effects of one of the predicted weather conditions as determined and output in a graphical format according to an exemplary embodiment of the present invention. As shown in Figure 6, the forecast weather conditions are for rain forecast during the time period of May 2017. As shown, the predicted impact of forecasting rain in various locations is superimposed on a map by comparing the maximum forecast rainfall during that time period with the threshold of rain in each location of forecasting rainfall (as described above) Judge). In the example shown in Figure 6, there are 10 thresholds for 10 groups. Cohort 10 represents the highest predicted impact, which represents one of the rains that rarely occurs in the location (high recurring time interval) and has a large predicted observable impact (based on the correlation described above). Cohorts 1 to 9 represent lower predicted impacts, which means rainfall that occurs more frequently in the site and / or has a lower predicted observable impact. As shown in Figure 7, the forecast weather conditions are for rain forecast during the summer period of 2017. The predicted impact of forecasted rain in each location is determined by comparing the maximum forecasted rainfall during that time period with the threshold of rain in each location of the forecasted rainfall (determined as described above). In the example shown in Figure 7, there are 10 thresholds for 10 groups. Cohort 10 represents the highest predicted impact, which represents one of the rains that rarely occurs in the location (high recurring time interval) and has a large predicted observable impact (based on the correlation described above). Cohorts 1 to 9 represent lower predicted impacts, which means rainfall that occurs more frequently in the site and / or has a lower predicted observable impact. FIG. 8A shows an example of forecast weather conditions, specifically snowfall during the time period of March 13, 2017. FIG. 8B illustrates the predicted effects of the forecast weather conditions shown in FIG. 8A according to an exemplary embodiment of the present invention. FIG. 9A shows another example of forecast weather conditions, once again snowfall during the time period of March 13, 2017. FIG. 9B illustrates the predicted effects of the forecast weather conditions shown in FIG. 9A according to an exemplary embodiment of the present invention. FIG. 10A shows another example of a forecast weather condition, once again snowfall during the time period of March 13, 2017. FIG. 10B illustrates the predicted effects of the forecast weather conditions shown in FIG. 10A according to an exemplary embodiment of the present invention. As shown in Figures 8A to 8B, 9A to 9B, and 10A to 10B, the predicted impact of forecast weather conditions is not only related to the magnitude of these forecast weather conditions, but also to the characteristics of these specific locations, The most significant is the recurring time interval of these forecast weather conditions of these magnitudes in these locations. The hazard index analysis system 100 may also be used to output an alert based on the impact of forecast weather conditions (as opposed to solely based on the severity of such forecast weather conditions). For example, the hazard index analysis system 100 can also be used to output an alert to a user in the event that the impact of a forecast weather condition exceeds one of the thresholds specified by a user. Alarms can be output via user interface 190, email, SMS, smart phone notifications, etc. 12 to 14 illustrate locations of alarms that can be output based on predicted weather conditions (in this example, predicted weather conditions by Hurricane Matthew) according to an exemplary embodiment of the present invention. The hazard index analysis system 100 may also use a procedure similar to the one described above for forecasting weather events to predict the effects of forecasting environmental events. FIG. 15 is a flowchart of a procedure 1500 for predicting the effects of forecasting environmental conditions. Similar to the routine 300, the routine 1500 may be executed by the analysis unit 180. Similar to step 302, observable effects of at least some of the past environmental events are determined in step 1502. Similar to step 304, the observable effects of each of past environmental events are weighted by the population in step 1504. Similar to step 306, one or more relevant environmental conditions are determined in step 1506. Similar to step 308, the regression frequency of each environmental condition is determined in step 1508. Similar to step 310, a correlation between the past environmental conditions and the observable effects of the past environmental conditions is determined for each of the relevant environmental conditions in step 1510. Similar to step 312, the predicted observable effects of each of the past environmental conditions are calculated in step 1512. Similar to step 314, the predicted impact of past environmental event recurrence is determined in step 1514. Similar to step 316, in step 1516, past environmental events are ranked according to the risk of recurring environmental conditions. Similar to step 318, past environmental events are grouped in step 1518 based on the predicted impact of past weather event recurrences. Similar to step 320, the threshold of each group is determined in step 1520. Similar to step 322, the threshold of the location of past environmental events for additional geographic locations may be interpolated in step 1522. Similar to step 324, the predicted environmental conditions are received in step 1524. Similar to step 326, the predicted impact of the predicted environmental conditions is determined in step 1526. As described above, the hazard index analysis system 100 may output a predicted impact of the predicted environmental conditions and / or output an alert based on the predicted impact of the predicted environmental conditions. FIG. 16 is a flowchart of a procedure 1600 for predicting the effects of forecasting geological conditions. Similar to the routine 300, the routine 1600 may be executed by the analysis unit 180. Similar to step 302, observable effects of at least some of the past geological events are determined in step 1602. Similar to step 304, the observable impact of each of the past geological events is population weighted in step 1604. Similar to step 306, one or more relevant geological conditions are determined in step 1606. Similar to step 308, in step 1608, the regression frequency of the geographical conditions is determined. Similar to step 310, a correlation between the past geological conditions and the observable effects of the past geological conditions is determined for each of the relevant geological conditions in step 1610. Similar to step 312, the predicted observable effects of each of the past geological conditions are calculated in step 1612. Similar to step 314, the predicted impact of past geological event recurrence is determined in step 1614. Similar to step 316, in step 1616, past geological events are ranked according to the risk of recurring geological conditions. Similar to step 318, past geological events are grouped in step 1618 based on the predicted impact of past weather event recurrences. Similar to step 320, the threshold of each group is determined in step 1620. Similar to step 322, the threshold values of the locations of past geological events for additional geographical locations may be interpolated in step 1622. Similar to step 324, the predicted geological conditions are received in step 1624. Similar to step 326, the predicted impact of the predicted geological conditions is determined in step 1626. As described above, the hazard index analysis system 100 may output the predicted impact of the predicted geological conditions and / or output an alert based on the predicted impact of the predicted geological conditions. Although a preferred embodiment has been described above, those skilled in the art who have reviewed the invention will readily understand that other embodiments can be implemented within the scope of the invention. The disclosure of specific technologies is also illustrative and not restrictive. Therefore, the present invention should be understood as being limited only by the scope of the invention patent application.

100‧‧‧ Hazard Index Analysis System
110‧‧‧Database
112‧‧‧ Historical Weather Information
114‧‧‧ historical weather impact data
116‧‧‧Forecast weather conditions
122‧‧‧ Historical and Environmental Information
124‧‧‧ Historical Environmental Impact Data
126‧‧‧Forecasting environmental conditions
132‧‧‧ Historical Geological Data
134‧‧‧ historical geological impact data
136‧‧‧Forecasting Geological Conditions
180‧‧‧analysis unit
190‧‧‧ Graphic User Interface
200‧‧‧ architecture
210‧‧‧Server
212‧‧‧ Internal storage device
214‧‧‧Processor
220‧‧‧Storage device
230‧‧‧Internet
240‧‧‧ remote computer system
250‧‧‧Personal System / PC System
252‧‧‧ Internal storage device
254‧‧‧Processor
256‧‧‧output device
258‧‧‧Input device
260‧‧‧Mobile Computer System
262‧‧‧ Internal storage device
264‧‧‧Processor
266‧‧‧Output device
268‧‧‧ input device
300‧‧‧ Procedure
302‧‧‧step
304‧‧‧step
306‧‧‧step
308‧‧‧step
310‧‧‧step
312‧‧‧step
314‧‧‧step
316‧‧‧step
318‧‧‧step
320‧‧‧ steps
322‧‧‧step
324‧‧‧step
326‧‧‧step
1500‧‧‧Procedure
1502‧‧‧step
1504‧‧‧step
1506‧‧‧step
1508‧‧‧step
1510‧‧‧step
1512‧‧‧step
1514‧‧‧step
1516‧‧‧step
1518‧‧‧step
1520‧‧‧step
1522‧‧‧ steps
1524‧‧‧step
1526‧‧‧step
1600‧‧‧program
1602‧‧‧step
1604‧‧‧step
1606‧‧‧step
1608‧‧‧step
1610‧‧‧step
1612‧‧‧step
1614‧‧‧step
1616‧‧‧step
1618‧‧‧step
1620‧‧‧step
1622‧‧‧step
1624‧‧‧step
1626‧‧‧step

The aspects of the exemplary embodiments can be better understood with reference to the accompanying drawings. The components in the figures are not necessarily to scale, and instead focus on the principle of the exemplary embodiment, in which: FIG. 1 is a block diagram illustrating a risk index analysis system according to an exemplary embodiment of the present invention ; FIG. 2 is a block diagram showing an overview of a structure of a hazard index analysis system according to an exemplary embodiment of the present invention; FIG. 3 is a diagram for predicting the effects of forecasting weather conditions according to an exemplary embodiment of the present invention A flowchart of a program; FIG. 4 is a table of weather events in a ranked and grouped place according to an exemplary embodiment of the present invention; FIG. 5 is a table of weather events according to an exemplary embodiment of the present invention A table of one of the weather events in another place that is ranked and grouped; Figures 6 to 7 show the predicted effects of forecasting weather conditions as determined and output in a graphical format according to an exemplary embodiment of the present invention; Figure 8A shows the forecast An example of weather conditions; FIG. 8B illustrates the predicted effects of the forecast weather conditions shown in FIG. 8A according to an exemplary embodiment of the present invention; FIG. 9A illustrates another embodiment of forecast weather conditions Figure 9B illustrates the predicted impact of forecast weather conditions shown in Figure 9A according to an exemplary embodiment of the present invention; Figure 10A illustrates another example of forecast weather conditions; Figure 10B illustrates an exemplary implementation according to the present invention The predicted impact of the forecast weather conditions shown in Figure 10A of the example; Figures 12 to 14 illustrate locations of alarms that can be output based on forecast weather conditions according to an exemplary embodiment of the present invention; Figure 15 is used to forecast environmental conditions for forecasting A flowchart of one of the procedures for the impact; and FIG. 16 is a flowchart of one of the procedures for predicting the impact of geological conditions.

300‧‧‧ Procedure

302‧‧‧step

304‧‧‧step

306‧‧‧step

308‧‧‧step

310‧‧‧step

312‧‧‧step

314‧‧‧step

316‧‧‧step

318‧‧‧step

320‧‧‧ steps

322‧‧‧step

324‧‧‧step

326‧‧‧step

Claims (15)

A method of predicting the effects of forecast weather conditions, the method comprising: receiving information indicating past weather events in a plurality of locations, each of the past weather events including one or more past weather conditions; receiving an indication of the past weather Information on the observable impact of at least some of the events; for each of the plurality of locations and each of the one or more weather conditions: determining that one of the past weather conditions in the plurality of locations reappears Time interval; determining the correlation between the past weather conditions and the observable impact of the past weather events; calculating one of the past weather conditions to predict the observable impact; by making the The predicted observable impact is multiplied by the recurring time interval of the past weather condition to calculate a predicted impact of each of the past weather conditions; based on the predicted impact of the past weather condition, the past effects are Weather events are grouped into a plurality of groups; and a threshold is determined for each of the plurality of groups; receiving forecast weather conditions; and Compare those forecast by the weather conditions and such threshold is determined for each of these groups of those who place such forecast the weather in the event of such determination and prediction of the forecast weather conditions. The method of claim 1, wherein a regression algorithm is used to determine the correlation between the past weather conditions and the observable impact of the past weather events. The method of claim 1, further comprising: population-weighting the observable impact of past weather events. The method of claim 1, further comprising: interpolating the thresholds of the plurality of locations to determine thresholds for additional locations. The method of claim 4, wherein a thresholding technique is used to interpolate the thresholds. The method of claim 1, wherein determining the threshold of each of the one or more weather conditions includes determining the threshold of each of the plurality of weather conditions and each of the plurality of locations. The method of claim 6, wherein the plurality of weather conditions include at least one of snow, rain, ice, wind, or temperature. A system for predicting the effects of forecast weather events, including: one or more databases that store: information indicating past weather events in a plurality of locations, each of which includes one or more Past weather conditions; and information indicating the observable impact of at least some of these past weather events; an analysis unit that targets each of the plurality of locations and each of the one or more weather conditions: determines the plural A recurring time interval for one of the past weather conditions in each of the locations; determining the correlation between the past weather conditions and the observable impact of the past weather events; calculating each of the past weather conditions One of them predicts an observable impact; calculates each of the past weather conditions to reproduce a predicted impact by multiplying the predicted observable impact of the past weather condition by the recurring time interval of the past weather condition; Grouping the past weather events into a plurality of groups based on the predicted impact of the past weather conditions recurrence; and determining each of the plurality of groups One of the thresholds; receiving forecasted weather conditions; and determining the thresholds by comparing the forecasted weather conditions with the thresholds determined by each of the groups in the locations for the forecasted weather events The forecast effect of such forecast weather conditions. The system of claim 8, wherein the analysis unit is further configured to determine a correlation between the past weather condition and the observable impact of the past weather event using a regression algorithm. The system of claim 8, wherein the analysis unit is further configured to: population-weight the observable impact of past weather events. As in the system of claim 8, wherein the analysis unit is further configured to interpolate the thresholds of the plurality of locations to determine thresholds for additional locations. The system of claim 11, wherein the analysis unit is further configured to interpolate the thresholds using a kriging technique. The system of claim 8, wherein the analysis unit is configured to determine a threshold value for each of the plurality of weather conditions in each of the plurality of locations. The system of claim 13, wherein the plurality of weather conditions include at least one of snow, rain, ice, wind, or temperature. A non-transitory computer-readable storage medium storing instructions that, when executed by a computer program, causes a computing device to: receive information indicating past weather events in a plurality of locations, each of these past weather events Contains one or more past weather conditions; receives information indicating the observable impact of at least some of these past weather events; for each of the plurality of locations and each of the one or more weather conditions: determine the plurality One of each of these past weather conditions in the location to reproduce the time interval; determine the correlation between the past weather condition and the observable impact of the past weather event; calculate one of the past weather events Predictable observable impact; calculating a predicted impact of each of the past weather events by multiplying the predicted observable impact of the past weather event by the recurring time interval of the past weather condition; based on the past Grouping the past weather events into a plurality of groups with the predicted effect of the recurring weather conditions; and determining each of the plurality of groups Threshold values are received; forecast weather conditions are received; and the thresholds are determined by comparing the forecast weather conditions with those threshold values determined by each of the groups in the locations for the forecast weather events The forecast effect of forecasting weather conditions.